1 files changed, 470 insertions, 227 deletions

diff --git a/pathspec.c b/pathspec.c
index 49a53607bb..303efda837 100644
--- a/pathspec.c
+++ b/pathspec.c
@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "dir.h"
 #include "pathspec.h"
+#include "attr.h"
 
 /*
  * Finds which of the given pathspecs match items in the index.
@@ -67,20 +68,20 @@ static struct pathspec_magic {
 	char mnemonic; /* this cannot be ':'! */
 	const char *name;
 } pathspec_magic[] = {
-	{ PATHSPEC_FROMTOP, '/', "top" },
-	{ PATHSPEC_LITERAL,   0, "literal" },
-	{ PATHSPEC_GLOB,   '\0', "glob" },
-	{ PATHSPEC_ICASE,  '\0', "icase" },
-	{ PATHSPEC_EXCLUDE, '!', "exclude" },
+	{ PATHSPEC_FROMTOP,  '/', "top" },
+	{ PATHSPEC_LITERAL, '\0', "literal" },
+	{ PATHSPEC_GLOB,    '\0', "glob" },
+	{ PATHSPEC_ICASE,   '\0', "icase" },
+	{ PATHSPEC_EXCLUDE,  '!', "exclude" },
+	{ PATHSPEC_ATTR,    '\0', "attr" },
 };
 
-static void prefix_short_magic(struct strbuf *sb, int prefixlen,
-			       unsigned short_magic)
+static void prefix_magic(struct strbuf *sb, int prefixlen, unsigned magic)
 {
 	int i;
 	strbuf_addstr(sb, ":(");
 	for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++)
-		if (short_magic & pathspec_magic[i].bit) {
+		if (magic & pathspec_magic[i].bit) {
 			if (sb->buf[sb->len - 1] != '(')
 				strbuf_addch(sb, ',');
 			strbuf_addstr(sb, pathspec_magic[i].name);
@@ -88,54 +89,171 @@ static void prefix_short_magic(struct strbuf *sb, int prefixlen,
 	strbuf_addf(sb, ",prefix:%d)", prefixlen);
 }
 
-/*
- * Take an element of a pathspec and check for magic signatures.
- * Append the result to the prefix. Return the magic bitmap.
- *
- * For now, we only parse the syntax and throw out anything other than
- * "top" magic.
- *
- * NEEDSWORK: This needs to be rewritten when we start migrating
- * get_pathspec() users to use the "struct pathspec" interface.  For
- * example, a pathspec element may be marked as case-insensitive, but
- * the prefix part must always match literally, and a single stupid
- * string cannot express such a case.
- */
-static unsigned prefix_pathspec(struct pathspec_item *item,
-				unsigned *p_short_magic,
-				const char **raw, unsigned flags,
-				const char *prefix, int prefixlen,
-				const char *elt)
+static size_t strcspn_escaped(const char *s, const char *stop)
 {
-	static int literal_global = -1;
-	static int glob_global = -1;
-	static int noglob_global = -1;
-	static int icase_global = -1;
-	unsigned magic = 0, short_magic = 0, global_magic = 0;
-	const char *copyfrom = elt, *long_magic_end = NULL;
-	char *match;
-	int i, pathspec_prefix = -1;
+	const char *i;
+
+	for (i = s; *i; i++) {
+		/* skip the escaped character */
+		if (i[0] == '\\' && i[1]) {
+			i++;
+			continue;
+		}
+
+		if (strchr(stop, *i))
+			break;
+	}
+	return i - s;
+}
+
+static inline int invalid_value_char(const char ch)
+{
+	if (isalnum(ch) || strchr(",-_", ch))
+		return 0;
+	return -1;
+}
+
+static char *attr_value_unescape(const char *value)
+{
+	const char *src;
+	char *dst, *ret;
+
+	ret = xmallocz(strlen(value));
+	for (src = value, dst = ret; *src; src++, dst++) {
+		if (*src == '\\') {
+			if (!src[1])
+				die(_("Escape character '\\' not allowed as "
+				      "last character in attr value"));
+			src++;
+		}
+		if (invalid_value_char(*src))
+			die("cannot use '%c' for value matching", *src);
+		*dst = *src;
+	}
+	*dst = '\0';
+	return ret;
+}
+
+static void parse_pathspec_attr_match(struct pathspec_item *item, const char *value)
+{
+	struct string_list_item *si;
+	struct string_list list = STRING_LIST_INIT_DUP;
+
+	if (item->attr_check || item->attr_match)
+		die(_("Only one 'attr:' specification is allowed."));
+
+	if (!value || !*value)
+		die(_("attr spec must not be empty"));
+
+	string_list_split(&list, value, ' ', -1);
+	string_list_remove_empty_items(&list, 0);
+
+	item->attr_check = attr_check_alloc();
+	item->attr_match = xcalloc(list.nr, sizeof(struct attr_match));
+
+	for_each_string_list_item(si, &list) {
+		size_t attr_len;
+		char *attr_name;
+		const struct git_attr *a;
+
+		int j = item->attr_match_nr++;
+		const char *attr = si->string;
+		struct attr_match *am = &item->attr_match[j];
+
+		switch (*attr) {
+		case '!':
+			am->match_mode = MATCH_UNSPECIFIED;
+			attr++;
+			attr_len = strlen(attr);
+			break;
+		case '-':
+			am->match_mode = MATCH_UNSET;
+			attr++;
+			attr_len = strlen(attr);
+			break;
+		default:
+			attr_len = strcspn(attr, "=");
+			if (attr[attr_len] != '=')
+				am->match_mode = MATCH_SET;
+			else {
+				const char *v = &attr[attr_len + 1];
+				am->match_mode = MATCH_VALUE;
+				am->value = attr_value_unescape(v);
+			}
+			break;
+		}
+
+		attr_name = xmemdupz(attr, attr_len);
+		a = git_attr(attr_name);
+		if (!a)
+			die(_("invalid attribute name %s"), attr_name);
+
+		attr_check_append(item->attr_check, a);
+
+		free(attr_name);
+	}
+
+	if (item->attr_check->nr != item->attr_match_nr)
+		die("BUG: should have same number of entries");
+
+	string_list_clear(&list, 0);
+}
+
+static inline int get_literal_global(void)
+{
+	static int literal = -1;
+
+	if (literal < 0)
+		literal = git_env_bool(GIT_LITERAL_PATHSPECS_ENVIRONMENT, 0);
+
+	return literal;
+}
+
+static inline int get_glob_global(void)
+{
+	static int glob = -1;
+
+	if (glob < 0)
+		glob = git_env_bool(GIT_GLOB_PATHSPECS_ENVIRONMENT, 0);
+
+	return glob;
+}
+
+static inline int get_noglob_global(void)
+{
+	static int noglob = -1;
+
+	if (noglob < 0)
+		noglob = git_env_bool(GIT_NOGLOB_PATHSPECS_ENVIRONMENT, 0);
+
+	return noglob;
+}
+
+static inline int get_icase_global(void)
+{
+	static int icase = -1;
+
+	if (icase < 0)
+		icase = git_env_bool(GIT_ICASE_PATHSPECS_ENVIRONMENT, 0);
+
+	return icase;
+}
+
+static int get_global_magic(int element_magic)
+{
+	int global_magic = 0;
 
-	if (literal_global < 0)
-		literal_global = git_env_bool(GIT_LITERAL_PATHSPECS_ENVIRONMENT, 0);
-	if (literal_global)
+	if (get_literal_global())
 		global_magic |= PATHSPEC_LITERAL;
 
-	if (glob_global < 0)
-		glob_global = git_env_bool(GIT_GLOB_PATHSPECS_ENVIRONMENT, 0);
-	if (glob_global)
+	/* --glob-pathspec is overridden by :(literal) */
+	if (get_glob_global() && !(element_magic & PATHSPEC_LITERAL))
 		global_magic |= PATHSPEC_GLOB;
 
-	if (noglob_global < 0)
-		noglob_global = git_env_bool(GIT_NOGLOB_PATHSPECS_ENVIRONMENT, 0);
-
-	if (glob_global && noglob_global)
+	if (get_glob_global() && get_noglob_global())
 		die(_("global 'glob' and 'noglob' pathspec settings are incompatible"));
 
-
-	if (icase_global < 0)
-		icase_global = git_env_bool(GIT_ICASE_PATHSPECS_ENVIRONMENT, 0);
-	if (icase_global)
+	if (get_icase_global())
 		global_magic |= PATHSPEC_ICASE;
 
 	if ((global_magic & PATHSPEC_LITERAL) &&
@@ -143,84 +261,219 @@ static unsigned prefix_pathspec(struct pathspec_item *item,
 		die(_("global 'literal' pathspec setting is incompatible "
 		      "with all other global pathspec settings"));
 
-	if (flags & PATHSPEC_LITERAL_PATH)
-		global_magic = 0;
+	/* --noglob-pathspec adds :(literal) _unless_ :(glob) is specified */
+	if (get_noglob_global() && !(element_magic & PATHSPEC_GLOB))
+		global_magic |= PATHSPEC_LITERAL;
 
-	if (elt[0] != ':' || literal_global ||
-	    (flags & PATHSPEC_LITERAL_PATH)) {
-		; /* nothing to do */
-	} else if (elt[1] == '(') {
-		/* longhand */
-		const char *nextat;
-		for (copyfrom = elt + 2;
-		     *copyfrom && *copyfrom != ')';
-		     copyfrom = nextat) {
-			size_t len = strcspn(copyfrom, ",)");
-			if (copyfrom[len] == ',')
-				nextat = copyfrom + len + 1;
-			else
-				/* handle ')' and '\0' */
-				nextat = copyfrom + len;
-			if (!len)
-				continue;
-			for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++) {
-				if (strlen(pathspec_magic[i].name) == len &&
-				    !strncmp(pathspec_magic[i].name, copyfrom, len)) {
-					magic |= pathspec_magic[i].bit;
-					break;
-				}
-				if (starts_with(copyfrom, "prefix:")) {
-					char *endptr;
-					pathspec_prefix = strtol(copyfrom + 7,
-								 &endptr, 10);
-					if (endptr - copyfrom != len)
-						die(_("invalid parameter for pathspec magic 'prefix'"));
-					/* "i" would be wrong, but it does not matter */
-					break;
-				}
+	return global_magic;
+}
+
+/*
+ * Parse the pathspec element looking for long magic
+ *
+ * saves all magic in 'magic'
+ * if prefix magic is used, save the prefix length in 'prefix_len'
+ * returns the position in 'elem' after all magic has been parsed
+ */
+static const char *parse_long_magic(unsigned *magic, int *prefix_len,
+				    struct pathspec_item *item,
+				    const char *elem)
+{
+	const char *pos;
+	const char *nextat;
+
+	for (pos = elem + 2; *pos && *pos != ')'; pos = nextat) {
+		size_t len = strcspn_escaped(pos, ",)");
+		int i;
+
+		if (pos[len] == ',')
+			nextat = pos + len + 1; /* handle ',' */
+		else
+			nextat = pos + len; /* handle ')' and '\0' */
+
+		if (!len)
+			continue;
+
+		if (starts_with(pos, "prefix:")) {
+			char *endptr;
+			*prefix_len = strtol(pos + 7, &endptr, 10);
+			if (endptr - pos != len)
+				die(_("invalid parameter for pathspec magic 'prefix'"));
+			continue;
+		}
+
+		if (starts_with(pos, "attr:")) {
+			char *attr_body = xmemdupz(pos + 5, len - 5);
+			parse_pathspec_attr_match(item, attr_body);
+			*magic |= PATHSPEC_ATTR;
+			free(attr_body);
+			continue;
+		}
+
+		for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++) {
+			if (strlen(pathspec_magic[i].name) == len &&
+			    !strncmp(pathspec_magic[i].name, pos, len)) {
+				*magic |= pathspec_magic[i].bit;
+				break;
 			}
-			if (ARRAY_SIZE(pathspec_magic) <= i)
-				die(_("Invalid pathspec magic '%.*s' in '%s'"),
-				    (int) len, copyfrom, elt);
 		}
-		if (*copyfrom != ')')
-			die(_("Missing ')' at the end of pathspec magic in '%s'"), elt);
-		long_magic_end = copyfrom;
-		copyfrom++;
-	} else {
-		/* shorthand */
-		for (copyfrom = elt + 1;
-		     *copyfrom && *copyfrom != ':';
-		     copyfrom++) {
-			char ch = *copyfrom;
 
-			if (!is_pathspec_magic(ch))
+		if (ARRAY_SIZE(pathspec_magic) <= i)
+			die(_("Invalid pathspec magic '%.*s' in '%s'"),
+			    (int) len, pos, elem);
+	}
+
+	if (*pos != ')')
+		die(_("Missing ')' at the end of pathspec magic in '%s'"),
+		    elem);
+	pos++;
+
+	return pos;
+}
+
+/*
+ * Parse the pathspec element looking for short magic
+ *
+ * saves all magic in 'magic'
+ * returns the position in 'elem' after all magic has been parsed
+ */
+static const char *parse_short_magic(unsigned *magic, const char *elem)
+{
+	const char *pos;
+
+	for (pos = elem + 1; *pos && *pos != ':'; pos++) {
+		char ch = *pos;
+		int i;
+
+		/* Special case alias for '!' */
+		if (ch == '^') {
+			*magic |= PATHSPEC_EXCLUDE;
+			continue;
+		}
+
+		if (!is_pathspec_magic(ch))
+			break;
+
+		for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++) {
+			if (pathspec_magic[i].mnemonic == ch) {
+				*magic |= pathspec_magic[i].bit;
 				break;
-			for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++)
-				if (pathspec_magic[i].mnemonic == ch) {
-					short_magic |= pathspec_magic[i].bit;
-					break;
-				}
-			if (ARRAY_SIZE(pathspec_magic) <= i)
-				die(_("Unimplemented pathspec magic '%c' in '%s'"),
-				    ch, elt);
+			}
 		}
-		if (*copyfrom == ':')
-			copyfrom++;
+
+		if (ARRAY_SIZE(pathspec_magic) <= i)
+			die(_("Unimplemented pathspec magic '%c' in '%s'"),
+			    ch, elem);
 	}
 
-	magic |= short_magic;
-	*p_short_magic = short_magic;
+	if (*pos == ':')
+		pos++;
 
-	/* --noglob-pathspec adds :(literal) _unless_ :(glob) is specified */
-	if (noglob_global && !(magic & PATHSPEC_GLOB))
-		global_magic |= PATHSPEC_LITERAL;
+	return pos;
+}
 
-	/* --glob-pathspec is overridden by :(literal) */
-	if ((global_magic & PATHSPEC_GLOB) && (magic & PATHSPEC_LITERAL))
-		global_magic &= ~PATHSPEC_GLOB;
+static const char *parse_element_magic(unsigned *magic, int *prefix_len,
+				       struct pathspec_item *item,
+				       const char *elem)
+{
+	if (elem[0] != ':' || get_literal_global())
+		return elem; /* nothing to do */
+	else if (elem[1] == '(')
+		/* longhand */
+		return parse_long_magic(magic, prefix_len, item, elem);
+	else
+		/* shorthand */
+		return parse_short_magic(magic, elem);
+}
 
-	magic |= global_magic;
+static void strip_submodule_slash_cheap(struct pathspec_item *item)
+{
+	if (item->len >= 1 && item->match[item->len - 1] == '/') {
+		int i = cache_name_pos(item->match, item->len - 1);
+
+		if (i >= 0 && S_ISGITLINK(active_cache[i]->ce_mode)) {
+			item->len--;
+			item->match[item->len] = '\0';
+		}
+	}
+}
+
+static void strip_submodule_slash_expensive(struct pathspec_item *item)
+{
+	int i;
+
+	for (i = 0; i < active_nr; i++) {
+		struct cache_entry *ce = active_cache[i];
+		int ce_len = ce_namelen(ce);
+
+		if (!S_ISGITLINK(ce->ce_mode))
+			continue;
+
+		if (item->len <= ce_len || item->match[ce_len] != '/' ||
+		    memcmp(ce->name, item->match, ce_len))
+			continue;
+
+		if (item->len == ce_len + 1) {
+			/* strip trailing slash */
+			item->len--;
+			item->match[item->len] = '\0';
+		} else {
+			die(_("Pathspec '%s' is in submodule '%.*s'"),
+			    item->original, ce_len, ce->name);
+		}
+	}
+}
+
+static void die_inside_submodule_path(struct pathspec_item *item)
+{
+	int i;
+
+	for (i = 0; i < active_nr; i++) {
+		struct cache_entry *ce = active_cache[i];
+		int ce_len = ce_namelen(ce);
+
+		if (!S_ISGITLINK(ce->ce_mode))
+			continue;
+
+		if (item->len < ce_len ||
+		    !(item->match[ce_len] == '/' || item->match[ce_len] == '\0') ||
+		    memcmp(ce->name, item->match, ce_len))
+			continue;
+
+		die(_("Pathspec '%s' is in submodule '%.*s'"),
+		    item->original, ce_len, ce->name);
+	}
+}
+
+/*
+ * Perform the initialization of a pathspec_item based on a pathspec element.
+ */
+static void init_pathspec_item(struct pathspec_item *item, unsigned flags,
+			       const char *prefix, int prefixlen,
+			       const char *elt)
+{
+	unsigned magic = 0, element_magic = 0;
+	const char *copyfrom = elt;
+	char *match;
+	int pathspec_prefix = -1;
+
+	item->attr_check = NULL;
+	item->attr_match = NULL;
+	item->attr_match_nr = 0;
+
+	/* PATHSPEC_LITERAL_PATH ignores magic */
+	if (flags & PATHSPEC_LITERAL_PATH) {
+		magic = PATHSPEC_LITERAL;
+	} else {
+		copyfrom = parse_element_magic(&element_magic,
+					       &pathspec_prefix,
+					       item,
+					       elt);
+		magic |= element_magic;
+		magic |= get_global_magic(element_magic);
+	}
+
+	item->magic = magic;
 
 	if (pathspec_prefix >= 0 &&
 	    (prefixlen || (prefix && *prefix)))
@@ -229,6 +482,7 @@ static unsigned prefix_pathspec(struct pathspec_item *item,
 	if ((magic & PATHSPEC_LITERAL) && (magic & PATHSPEC_GLOB))
 		die(_("%s: 'literal' and 'glob' are incompatible"), elt);
 
+	/* Create match string which will be used for pathspec matching */
 	if (pathspec_prefix >= 0) {
 		match = xstrdup(copyfrom);
 		prefixlen = pathspec_prefix;
@@ -236,69 +490,47 @@ static unsigned prefix_pathspec(struct pathspec_item *item,
 		match = xstrdup(copyfrom);
 		prefixlen = 0;
 	} else {
-		match = prefix_path_gently(prefix, prefixlen, &prefixlen, copyfrom);
+		match = prefix_path_gently(prefix, prefixlen,
+					   &prefixlen, copyfrom);
 		if (!match)
 			die(_("%s: '%s' is outside repository"), elt, copyfrom);
 	}
-	*raw = item->match = match;
+
+	item->match = match;
+	item->len = strlen(item->match);
+	item->prefix = prefixlen;
+
 	/*
 	 * Prefix the pathspec (keep all magic) and assign to
 	 * original. Useful for passing to another command.
 	 */
-	if (flags & PATHSPEC_PREFIX_ORIGIN) {
+	if ((flags & PATHSPEC_PREFIX_ORIGIN) &&
+	    prefixlen && !get_literal_global()) {
 		struct strbuf sb = STRBUF_INIT;
-		if (prefixlen && !literal_global) {
-			/* Preserve the actual prefix length of each pattern */
-			if (short_magic)
-				prefix_short_magic(&sb, prefixlen, short_magic);
-			else if (long_magic_end) {
-				strbuf_add(&sb, elt, long_magic_end - elt);
-				strbuf_addf(&sb, ",prefix:%d)", prefixlen);
-			} else
-				strbuf_addf(&sb, ":(prefix:%d)", prefixlen);
-		}
+
+		/* Preserve the actual prefix length of each pattern */
+		prefix_magic(&sb, prefixlen, element_magic);
+
 		strbuf_addstr(&sb, match);
 		item->original = strbuf_detach(&sb, NULL);
-	} else
-		item->original = elt;
-	item->len = strlen(item->match);
-	item->prefix = prefixlen;
-
-	if ((flags & PATHSPEC_STRIP_SUBMODULE_SLASH_CHEAP) &&
-	    (item->len >= 1 && item->match[item->len - 1] == '/') &&
-	    (i = cache_name_pos(item->match, item->len - 1)) >= 0 &&
-	    S_ISGITLINK(active_cache[i]->ce_mode)) {
-		item->len--;
-		match[item->len] = '\0';
+	} else {
+		item->original = xstrdup(elt);
 	}
 
+	if (flags & PATHSPEC_STRIP_SUBMODULE_SLASH_CHEAP)
+		strip_submodule_slash_cheap(item);
+
 	if (flags & PATHSPEC_STRIP_SUBMODULE_SLASH_EXPENSIVE)
-		for (i = 0; i < active_nr; i++) {
-			struct cache_entry *ce = active_cache[i];
-			int ce_len = ce_namelen(ce);
-
-			if (!S_ISGITLINK(ce->ce_mode))
-				continue;
-
-			if (item->len <= ce_len || match[ce_len] != '/' ||
-			    memcmp(ce->name, match, ce_len))
-				continue;
-			if (item->len == ce_len + 1) {
-				/* strip trailing slash */
-				item->len--;
-				match[item->len] = '\0';
-			} else
-				die (_("Pathspec '%s' is in submodule '%.*s'"),
-				     elt, ce_len, ce->name);
-		}
+		strip_submodule_slash_expensive(item);
 
-	if (magic & PATHSPEC_LITERAL)
+	if (magic & PATHSPEC_LITERAL) {
 		item->nowildcard_len = item->len;
-	else {
+	} else {
 		item->nowildcard_len = simple_length(item->match);
 		if (item->nowildcard_len < prefixlen)
 			item->nowildcard_len = prefixlen;
 	}
+
 	item->flags = 0;
 	if (magic & PATHSPEC_GLOB) {
 		/*
@@ -313,9 +545,18 @@ static unsigned prefix_pathspec(struct pathspec_item *item,
 	}
 
 	/* sanity checks, pathspec matchers assume these are sane */
-	assert(item->nowildcard_len <= item->len &&
-	       item->prefix         <= item->len);
-	return magic;
+	if (item->nowildcard_len > item->len ||
+	    item->prefix         > item->len) {
+		/*
+		 * This case can be triggered by the user pointing us to a
+		 * pathspec inside a submodule, which is an input error.
+		 * Detect that here and complain, but fallback in the
+		 * non-submodule case to a BUG, as we have no idea what
+		 * would trigger that.
+		 */
+		die_inside_submodule_path(item);
+		die ("BUG: item->nowildcard_len > item->len || item->prefix > item->len)");
+	}
 }
 
 static int pathspec_item_cmp(const void *a_, const void *b_)
@@ -328,22 +569,22 @@ static int pathspec_item_cmp(const void *a_, const void *b_)
 }
 
 static void NORETURN unsupported_magic(const char *pattern,
-				       unsigned magic,
-				       unsigned short_magic)
+				       unsigned magic)
 {
 	struct strbuf sb = STRBUF_INIT;
-	int i, n;
-	for (n = i = 0; i < ARRAY_SIZE(pathspec_magic); i++) {
+	int i;
+	for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++) {
 		const struct pathspec_magic *m = pathspec_magic + i;
 		if (!(magic & m->bit))
 			continue;
 		if (sb.len)
-			strbuf_addch(&sb, ' ');
-		if (short_magic & m->bit)
-			strbuf_addf(&sb, "'%c'", m->mnemonic);
+			strbuf_addstr(&sb, ", ");
+
+		if (m->mnemonic)
+			strbuf_addf(&sb, _("'%s' (mnemonic: '%c')"),
+				    m->name, m->mnemonic);
 		else
 			strbuf_addf(&sb, "'%s'", m->name);
-		n++;
 	}
 	/*
 	 * We may want to substitute "this command" with a command
@@ -364,7 +605,7 @@ void parse_pathspec(struct pathspec *pathspec,
 {
 	struct pathspec_item *item;
 	const char *entry = argv ? *argv : NULL;
-	int i, n, prefixlen, nr_exclude = 0;
+	int i, n, prefixlen, warn_empty_string, nr_exclude = 0;
 
 	memset(pathspec, 0, sizeof(*pathspec));
 
@@ -381,8 +622,6 @@ void parse_pathspec(struct pathspec *pathspec,
 
 	/* No arguments with prefix -> prefix pathspec */
 	if (!entry) {
-		static const char *raw[2];
-
 		if (flags & PATHSPEC_PREFER_FULL)
 			return;
 
@@ -390,43 +629,39 @@ void parse_pathspec(struct pathspec *pathspec,
 			die("BUG: PATHSPEC_PREFER_CWD requires arguments");
 
 		pathspec->items = item = xcalloc(1, sizeof(*item));
-		item->match = prefix;
-		item->original = prefix;
+		item->match = xstrdup(prefix);
+		item->original = xstrdup(prefix);
 		item->nowildcard_len = item->len = strlen(prefix);
 		item->prefix = item->len;
-		raw[0] = prefix;
-		raw[1] = NULL;
 		pathspec->nr = 1;
-		pathspec->_raw = raw;
 		return;
 	}
 
 	n = 0;
-	while (argv[n])
+	warn_empty_string = 1;
+	while (argv[n]) {
+		if (*argv[n] == '\0' && warn_empty_string) {
+			warning(_("empty strings as pathspecs will be made invalid in upcoming releases. "
+				  "please use . instead if you meant to match all paths"));
+			warn_empty_string = 0;
+		}
 		n++;
+	}
 
 	pathspec->nr = n;
-	ALLOC_ARRAY(pathspec->items, n);
+	ALLOC_ARRAY(pathspec->items, n + 1);
 	item = pathspec->items;
-	pathspec->_raw = argv;
 	prefixlen = prefix ? strlen(prefix) : 0;
 
 	for (i = 0; i < n; i++) {
-		unsigned short_magic;
 		entry = argv[i];
 
-		item[i].magic = prefix_pathspec(item + i, &short_magic,
-						argv + i, flags,
-						prefix, prefixlen, entry);
-		if ((flags & PATHSPEC_LITERAL_PATH) &&
-		    !(magic_mask & PATHSPEC_LITERAL))
-			item[i].magic |= PATHSPEC_LITERAL;
+		init_pathspec_item(item + i, flags, prefix, prefixlen, entry);
+
 		if (item[i].magic & PATHSPEC_EXCLUDE)
 			nr_exclude++;
 		if (item[i].magic & magic_mask)
-			unsupported_magic(entry,
-					  item[i].magic & magic_mask,
-					  short_magic);
+			unsupported_magic(entry, item[i].magic & magic_mask);
 
 		if ((flags & PATHSPEC_SYMLINK_LEADING_PATH) &&
 		    has_symlink_leading_path(item[i].match, item[i].len)) {
@@ -438,58 +673,66 @@ void parse_pathspec(struct pathspec *pathspec,
 		pathspec->magic |= item[i].magic;
 	}
 
-	if (nr_exclude == n)
-		die(_("There is nothing to exclude from by :(exclude) patterns.\n"
-		      "Perhaps you forgot to add either ':/' or '.' ?"));
-
+	/*
+	 * If everything is an exclude pattern, add one positive pattern
+	 * that matches everyting. We allocated an extra one for this.
+	 */
+	if (nr_exclude == n) {
+		int plen = (!(flags & PATHSPEC_PREFER_CWD)) ? 0 : prefixlen;
+		init_pathspec_item(item + n, 0, prefix, plen, "");
+		pathspec->nr++;
+	}
 
 	if (pathspec->magic & PATHSPEC_MAXDEPTH) {
 		if (flags & PATHSPEC_KEEP_ORDER)
 			die("BUG: PATHSPEC_MAXDEPTH_VALID and PATHSPEC_KEEP_ORDER are incompatible");
-		qsort(pathspec->items, pathspec->nr,
-		      sizeof(struct pathspec_item), pathspec_item_cmp);
+		QSORT(pathspec->items, pathspec->nr, pathspec_item_cmp);
 	}
 }
 
-/*
- * N.B. get_pathspec() is deprecated in favor of the "struct pathspec"
- * based interface - see pathspec.c:parse_pathspec().
- *
- * Arguments:
- *  - prefix - a path relative to the root of the working tree
- *  - pathspec - a list of paths underneath the prefix path
- *
- * Iterates over pathspec, prepending each path with prefix,
- * and return the resulting list.
- *
- * If pathspec is empty, return a singleton list containing prefix.
- *
- * If pathspec and prefix are both empty, return an empty list.
- *
- * This is typically used by built-in commands such as add.c, in order
- * to normalize argv arguments provided to the built-in into a list of
- * paths to process, all relative to the root of the working tree.
- */
-const char **get_pathspec(const char *prefix, const char **pathspec)
-{
-	struct pathspec ps;
-	parse_pathspec(&ps,
-		       PATHSPEC_ALL_MAGIC &
-		       ~(PATHSPEC_FROMTOP | PATHSPEC_LITERAL),
-		       PATHSPEC_PREFER_CWD,
-		       prefix, pathspec);
-	return ps._raw;
-}
-
 void copy_pathspec(struct pathspec *dst, const struct pathspec *src)
 {
+	int i, j;
+
 	*dst = *src;
 	ALLOC_ARRAY(dst->items, dst->nr);
 	COPY_ARRAY(dst->items, src->items, dst->nr);
+
+	for (i = 0; i < dst->nr; i++) {
+		struct pathspec_item *d = &dst->items[i];
+		struct pathspec_item *s = &src->items[i];
+
+		d->match = xstrdup(s->match);
+		d->original = xstrdup(s->original);
+
+		ALLOC_ARRAY(d->attr_match, d->attr_match_nr);
+		COPY_ARRAY(d->attr_match, s->attr_match, d->attr_match_nr);
+		for (j = 0; j < d->attr_match_nr; j++) {
+			const char *value = s->attr_match[j].value;
+			d->attr_match[j].value = xstrdup_or_null(value);
+		}
+
+		d->attr_check = attr_check_dup(s->attr_check);
+	}
 }
 
 void clear_pathspec(struct pathspec *pathspec)
 {
+	int i, j;
+
+	for (i = 0; i < pathspec->nr; i++) {
+		free(pathspec->items[i].match);
+		free(pathspec->items[i].original);
+
+		for (j = 0; j < pathspec->items[j].attr_match_nr; j++)
+			free(pathspec->items[i].attr_match[j].value);
+		free(pathspec->items[i].attr_match);
+
+		if (pathspec->items[i].attr_check)
+			attr_check_free(pathspec->items[i].attr_check);
+	}
+
 	free(pathspec->items);
 	pathspec->items = NULL;
+	pathspec->nr = 0;
 }